使用命令行编译打包运行MapReduce程序

本文地址：http://www.cnblogs.com/myresearch/p/mapreduce-compile-jar-run.html，转载请注明源地址。

对于如何编译WordCount.java，对于0.20 等旧版本版本的做法很常见，具体如下：

 javac -classpath /usr/local/hadoop/hadoop-1.0.1/hadoop-core-1.0.1.jar WordCount.java

但较新的 2.X 版本中，已经没有 hadoop-core*.jar 这个文件，因此编辑和打包自己的MapReduce程序与旧版本有所不同。

本文以 Hadoop 2.6环境下的WordCount实例来介绍 2.x 版本中如何编辑自己的MapReduce程序。

Hadoop 2.x 版本中的依赖 jar

Hadoop 2.x 版本中jar不再集中在一个 hadoop-core*.jar 中，而是分成多个 jar，如运行WordCount实例需要如下三个 jar:

• $HADOOP_HOME/share/hadoop/common/hadoop-common-2.6.0.jar

• $HADOOP_HOME/share/hadoop/mapreduce/hadoop-mapreduce-client-core-2.6.0.jar

• $HADOOP_HOME/share/hadoop/common/lib/commons-cli-1.2.jar

编译、打包 Hadoop MapReduce 程序

将上述 jar 添加至 classpath 路径：

hadoop@ubuntu:~$ export CLASSPATH="$HADOOP_HOME/home/hadoop/opt/hadoop-2.6.0/share/hadoop/common/hadoop-common-2.6.0.jar:$HADOOP_HOME/home/hadoop/opt/hadoop-2.6.0/share/hadoop/mapreduce/hadoop-mapreduce-client-core-2.6.0.jar:$HADOOP_HOME/home/hadoop/opt/hadoop-2.6.0/share/hadoop/common/lib/commons-cli-1.2.jar:$CLASSPATH"

接着就可以编译 WordCount.java 了（使用的是 2.6.0源码中的 WordCount.java）

文件位于/hadoop-2.6.0-src/hadoop-mapreduce-project/hadoop-mapreduce-examples/src/main/java/org/apache/hadoop/examples 中，

javac WordCount.java

编译时会有警告，可以忽略。编译后可以看到生成了几个.class文件。

/home/hadoop/opt/hadoop-2.6.0/share/hadoop/common/hadoop-common-2.6.0.jar(org/apache/hadoop/fs/Path.class): warning: Cannot find annotation method 'value()' in type 'LimitedPrivate': class file for org.apache.hadoop.classification.InterfaceAudience not found
1 warning
hadoop@ubuntu:~/opt/code$ ls
WordCount.class WordCount.java WordCount$MapClass.class WordCount$Reduce.class

接着把 .class 文件打包成 jar，才能在 Hadoop 中运行：

hadoop@ubuntu:~/opt/code$ jar -cvf WordCount.jar ./WordCount*.class
added manifest
adding: WordCount.class(in = 3363) (out= 1687)(deflated 49%)
adding: WordCount$MapClass.class(in = 1978) (out= 800)(deflated 59%)
adding: WordCount$Reduce.class(in = 1641) (out= 645)(deflated 60%)

创建HDFS所需的输入文件夹：

hadoop@ubuntu:~/opt/code$ mkdir input
hadoop@ubuntu:~/opt/code$ echo "Hello Hadoop Goodbye Hadoop" > ./input/file1
hadoop@ubuntu:~/opt/code$ echo "Hello World Bye World" > ./input/file2
hadoop@ubuntu:~/opt/code$ ls ./input
file1 file2

运行我们的wordcount程序：

hadoop@ubuntu:~$ cd ~/opt/code

hadoop@ubuntu:~/opt/code$ ~/opt/hadoop-2.6.0/bin/hadoop jar WordCount.jar org.apache.hadoop.examples.WordCount input output

程序运行完之后，检查我们的输出结果：

hadoop@ubuntu:~/opt/code$ ls ./output
part-r-00000  _SUCCESS
hadoop@ubuntu:~/opt/code$ cat ./output/part-r-00000

Bye 1
Goodbye 1
Hadoop 2
Hello 2
World 2

PS：WordCount.java 源代码如下：

package org.apache.hadoop.mapred;

import java.io.IOException;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

/**
 * This is an example Hadoop Map/Reduce application.
 * It reads the text input files, breaks each line into words
 * and counts them. The output is a locally sorted list of words and the 
 * count of how often they occurred.
 *
 * To run: bin/hadoop jar build/hadoop-examples.jar wordcount
 *            [-m <i>maps</i>] [-r <i>reduces</i>] <i>in-dir</i> <i>out-dir</i> 
 */
public class WordCount extends Configured implements Tool {
  
  /**
   * Counts the words in each line.
   * For each line of input, break the line into words and emit them as
   * (<b>word</b>, <b>1</b>).
   */
  public static class MapClass extends MapReduceBase
    implements Mapper<LongWritable, Text, Text, IntWritable> {
    
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();
    
    public void map(LongWritable key, Text value, 
                    OutputCollector<Text, IntWritable> output, 
                    Reporter reporter) throws IOException {
      String line = value.toString();
      StringTokenizer itr = new StringTokenizer(line);
      while (itr.hasMoreTokens()) {
        word.set(itr.nextToken());
        output.collect(word, one);
      }
    }
  }
  
  /**
   * A reducer class that just emits the sum of the input values.
   */
  public static class Reduce extends MapReduceBase
    implements Reducer<Text, IntWritable, Text, IntWritable> {
    
    public void reduce(Text key, Iterator<IntWritable> values,
                       OutputCollector<Text, IntWritable> output, 
                       Reporter reporter) throws IOException {
      int sum = 0;
      while (values.hasNext()) {
        sum += values.next().get();
      }
      output.collect(key, new IntWritable(sum));
    }
  }
  
  static int printUsage() {
    System.out.println("wordcount [-m <maps>] [-r <reduces>] <input> <output>");
    ToolRunner.printGenericCommandUsage(System.out);
    return -1;
  }
  
  /**
   * The main driver for word count map/reduce program.
   * Invoke this method to submit the map/reduce job.
   * @throws IOException When there is communication problems with the 
   *                     job tracker.
   */
  public int run(String[] args) throws Exception {
    JobConf conf = new JobConf(getConf(), WordCount.class);
    conf.setJobName("wordcount");
 
    // the keys are words (strings)
    conf.setOutputKeyClass(Text.class);
    // the values are counts (ints)
    conf.setOutputValueClass(IntWritable.class);
    
    conf.setMapperClass(MapClass.class);        
    conf.setCombinerClass(Reduce.class);
    conf.setReducerClass(Reduce.class);
    
    List<String> other_args = new ArrayList<String>();
    for(int i=0; i < args.length; ++i) {
      try {
        if ("-m".equals(args[i])) {
          conf.setNumMapTasks(Integer.parseInt(args[++i]));
        } else if ("-r".equals(args[i])) {
          conf.setNumReduceTasks(Integer.parseInt(args[++i]));
        } else {
          other_args.add(args[i]);
        }
      } catch (NumberFormatException except) {
        System.out.println("ERROR: Integer expected instead of " + args[i]);
        return printUsage();
      } catch (ArrayIndexOutOfBoundsException except) {
        System.out.println("ERROR: Required parameter missing from " +
                           args[i-1]);
        return printUsage();
      }
    }
    // Make sure there are exactly 2 parameters left.
    if (other_args.size() != 2) {
      System.out.println("ERROR: Wrong number of parameters: " +
                         other_args.size() + " instead of 2.");
      return printUsage();
    }
    FileInputFormat.setInputPaths(conf, other_args.get(0));
    FileOutputFormat.setOutputPath(conf, new Path(other_args.get(1)));
        
    JobClient.runJob(conf);
    return 0;
  }
  
  
  public static void main(String[] args) throws Exception {
    int res = ToolRunner.run(new Configuration(), new WordCount(), args);
    System.exit(res);
  }

}

参考资料

http://www.powerxing.com/hadoop-build-project-by-shell/

http://blog.sina.com.cn/s/blog_68cceb610101r6tg.html

http://www.cppblog.com/humanchao/archive/2014/05/27/207118.aspx